Static security scanner for LLM agents — prompt injection, MCP config auditing, taint analysis. 51 rules mapped to OWASP Agentic Top 10 (2026). Works with LangChain, CrewAI, AutoGen.
☆219Jul 4, 2026Updated last month
Alternatives and similar repositories for agent-audit
Users that are interested in agent-audit are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆30Jun 13, 2026Updated 2 months ago
- Official codebase for the paper "Auditing Agent Harness Safety"☆53May 19, 2026Updated 2 months ago
- Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks☆91Aug 3, 2026Updated 2 weeks ago
- [COLM 2025] JailDAM: Jailbreak Detection with Adaptive Memory for Vision-Language Model☆26Nov 25, 2025Updated 8 months ago
- Source code for the ACL'2025 paper titled "Unveiling privacy risks in llm agent memory"☆35Dec 2, 2025Updated 8 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- A Framework for Evaluating AI Agent Safety in Realistic Environments☆38Aug 10, 2026Updated last week
- [ICLR 2026] The official code for "Doxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Models"☆30Feb 7, 2026Updated 6 months ago
- ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis☆35Jul 10, 2026Updated last month
- OpenVul: An Open-Source Post-Training Framework for LLM-Based Vulnerability Detection☆49May 2, 2026Updated 3 months ago
- ☆48Dec 9, 2025Updated 8 months ago
- ☆23Updated this week
- An autonomous LLM-agent for large-scale, repository-level code auditing☆430Mar 12, 2026Updated 5 months ago
- Audit any agent decision across its past, present, and future, on one typed graph.☆21Jul 20, 2026Updated 3 weeks ago
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆753Jun 2, 2026Updated 2 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Official Implementation of "ToolSafe: Enhancing Tool Invocation Safety of LLM-based Agents via Proactive Step-level Guardrail and Feedbac…☆75Mar 25, 2026Updated 4 months ago
- ☆27Apr 28, 2026Updated 3 months ago
- ICSE2021 Submission☆13Aug 28, 2022Updated 3 years ago
- The Official Repository for Paper "HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents?"☆16May 2, 2026Updated 3 months ago
- [ACL 2025] Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints☆19May 23, 2025Updated last year
- The official code for "Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks".☆19Jun 24, 2026Updated last month
- ☆12May 6, 2022Updated 4 years ago
- [ICML 2026] Official implementation for paper: Learning Self-Correction in Vision–Language Models via Rollout Augmentation☆16Jun 4, 2026Updated 2 months ago
- Official codebase for the paper "WorldMemArena: Evaluating Multimodal Agent Memory Through Action–World Interaction"☆25May 29, 2026Updated 2 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- [ICLR'26 Oral] RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments☆59Feb 9, 2026Updated 6 months ago
- [ICML 2026] Official implementation for paper "Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Ag…☆32Jul 31, 2026Updated 2 weeks ago
- Free OpenClaw security scanner. 3,000+ agents audited. 3-Layer Audit Protocol. OWASP ASI 10/10 coverage. AI agent integrity layer.☆38May 24, 2026Updated 2 months ago
- SkillJect: Automating Stealthy Skill-Based Prompt Injection for Coding Agents with Trace-Driven Closed-Loop Refinement☆75Jun 11, 2026Updated 2 months ago
- ☆76Jun 18, 2026Updated 2 months ago
- AgentWard – Built for all, hardened for OpenClaw.☆64Jun 4, 2026Updated 2 months ago
- ☆23Jun 18, 2025Updated last year
- Agent Security Bench (ASB)☆285Apr 16, 2026Updated 4 months ago
- ☆26May 12, 2026Updated 3 months ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- [ACL 2025] LongSafety: Evaluating Long-Context Safety of Large Language Models☆16Jun 18, 2025Updated last year
- A Diagnostic Guardrail Framework for AI Agent Safety and Security☆681Jun 8, 2026Updated 2 months ago
- [ICLR'26] Building a Foundational Guardrail for General Agentic Systems via Synthetic Data☆48Oct 26, 2025Updated 9 months ago
- [CVPR'26] SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization☆22Feb 19, 2026Updated 6 months ago
- An end-to-end security evaluation framework tailored for real-world personalized agent.☆15Feb 28, 2026Updated 5 months ago
- ☆67May 21, 2025Updated last year
- LLM手撕代码合集☆23Mar 25, 2025Updated last year